moBRCA-net: a breast cancer subtype classification framework based on multi-omics attention neural networks

Abstract

Background Breast cancer is a highly heterogeneous disease that comprises multiple biological components. Owing its diversity, patients have different prognostic outcomes; hence, early diagnosis and accurate subtype prediction are critical for treatment. Standardized breast cancer subtyping systems, mainly based on single-omics datasets, have been developed to ensure proper treatment in a systematic manner. Recently, multi-omics data integration has attracted attention to provide a comprehensive view of patients but poses a challenge due to the high dimensionality. In recent years, deep learning-based approaches have been proposed, but they still present several limitations. Results In this study, we describe moBRCA-net, an interpretable deep learning-based breast cancer subtype classification framework that uses multi-omics datasets. Three omics datasets comprising gene expression, DNA methylation and microRNA expression data were integrated while considering the biological relationships among them, and a self-attention module was applied to each omics dataset to capture the relative importance of each feature. The features were then transformed to new representations considering the respective learned importance, allowing moBRCA-net to predict the subtype. Conclusions Experimental results confirmed that moBRCA-net has a significantly enhanced performance compared with other methods, and the effectiveness of multi-omics integration and omics-level attention were identified. moBRCA-net is publicly available at https://github.com/cbi-bioinfo/moBRCA-net.

Gene expression prognostic of early relapse risk in low‐risk B‐cell acute lymphoblastic leukaemia in children

“…Multi‐omics analyses could discover clinically relevant prognostic factors that might escape single‐omics analysis [ 44 , 45 , 46 ]. In the present study, we conducted a multi‐omics analysis of 87 children with low‐risk ETV6::RUNX1 ‐positive ALL from China.…”

Applying a Recurrent Neural Network-Based Deep Learning Model for Gene Expression Data Classification

“…The study [20] considers the application of deep learning methods to navigate the challenging landscape of breast cancer subtyping, with its intrinsic heterogeneity and consequent varied prognostic outcomes, by introducing moBRCA-net, an interpretable deep learning-based classification framework that harnesses multi-omics datasets-specifically, by integrating gene expression, DNA methylation, and microRNA expression data while respecting the biological interrelationships among them. By employing a self-attention module for each omics dataset to ascertain the relative importance of each feature and subsequently transforming these features into new representations based on learned importance, moBRCA-net aims to adeptly predict breast cancer subtypes, demonstrating notably enhanced performance and effective multi-omics integration in comparison with other methods, as substantiated by experimental results.…”

DeepKEGG: a multi-omics data integration framework with biological insights for cancer recurrence prediction and biomarker discovery

“…These multi-omics data bring unprecedented opportunities and challenges to cancer research [ 1–4 ]. Furthermore, the availability of large-scale multi-omics databases such as The Cancer Genome Atlas (TCGA) [ 5 ], Cancer Cell Line Encyclopedia (CCLE) [ 6 ] and Therapeutically Applicable Research to Generate Effective Treatments (TARGET) ( https://www.cancer.gov/ccg/research/genome-sequencing/target ) has opened up new possibilities for cancer subtype classification [ 7 , 8 ], biomarker discovery [ 9 , 10 ], drug development [ 11 , 12 ], etc. Multi-omics data integration can comprehensively unveil the molecular-level interconnections and mechanisms underlying cancer development.…”